metadata
library_name: transformers
language:
- es
license: apache-2.0
base_model: openai/whisper-medium
tags:
- generated_from_trainer
datasets:
- fixie-ai/common_voice_17_0
metrics:
- wer
model-index:
- name: Whisper Medium CV17 Es 50 steps- María Marrón
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice 17.0
type: fixie-ai/common_voice_17_0
args: 'config: es, split:test'
metrics:
- name: Wer
type: wer
value: 6.942025853850748
Whisper Medium CV17 Es 50 steps- María Marrón
This model is a fine-tuned version of openai/whisper-medium on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.5798
- Wer Ortho: 11.4657
- Cer Ortho: 3.2862
- Wer: 6.9420
- Cer: 2.3005
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 2
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 32
- total_train_batch_size: 64
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 5
- training_steps: 50
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Cer Ortho | Wer | Cer |
|---|---|---|---|---|---|---|---|
| 2.9481 | 0.2 | 10 | 1.7270 | 12.0729 | 3.6802 | 7.1193 | 2.5784 |
| 1.3731 | 0.4 | 20 | 1.0923 | 11.5624 | 3.3599 | 6.9948 | 2.3544 |
| 0.9897 | 0.6 | 30 | 0.8008 | 11.6923 | 3.3918 | 7.0571 | 2.3674 |
| 0.7372 | 0.8 | 40 | 0.6473 | 11.4720 | 3.3122 | 6.9293 | 2.3112 |
| 0.6275 | 1.0 | 50 | 0.5798 | 11.4657 | 3.2862 | 6.9420 | 2.3005 |
Framework versions
- Transformers 4.53.2
- Pytorch 2.6.0+cu124
- Datasets 2.14.4
- Tokenizers 0.21.2